CN113627280A - Method for monitoring and analyzing cyanobacterial bloom in lake shore zone based on video monitoring equipment - Google Patents
Method for monitoring and analyzing cyanobacterial bloom in lake shore zone based on video monitoring equipment Download PDFInfo
- Publication number
- CN113627280A CN113627280A CN202110834926.0A CN202110834926A CN113627280A CN 113627280 A CN113627280 A CN 113627280A CN 202110834926 A CN202110834926 A CN 202110834926A CN 113627280 A CN113627280 A CN 113627280A
- Authority
- CN
- China
- Prior art keywords
- bloom
- cyanobacterial bloom
- video monitoring
- time
- key frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 230000007246 mechanism Effects 0.000 claims abstract description 5
- 241000195493 Cryptophyta Species 0.000 claims description 31
- 238000012806 monitoring device Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 13
- 241000192710 Microcystis aeruginosa Species 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 7
- 241000192700 Cyanobacteria Species 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 abstract 1
- 230000006872 improvement Effects 0.000 description 9
- 230000008859 change Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000005286 illumination Methods 0.000 description 4
- 230000002265 prevention Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013481 data capture Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a method for monitoring and analyzing cyanobacterial bloom in a lake shore zone based on video monitoring equipment, which comprises the following steps: (1) arranging shore-based video monitoring equipment along the lake, continuously monitoring the cyanobacterial bloom information of key areas and key positions on the shore, periodically capturing key frame images, and transmitting the image data to a server in a wireless transmission mode; (2) designing and developing a digital image cyanobacterial bloom coverage accurate extraction algorithm based on a multithreading mechanism, and quickly and automatically extracting cyanobacterial bloom information (time, place, bloom range, strength and the like) based on video monitoring data; (3) based on the cyanobacterial bloom coverage extraction result of each monitoring point, identifying the point exceeding the standard through threshold comparison and realizing automatic alarm; and (3) constructing a topological relation between the video monitoring point positions and the coastal zone, and realizing near real-time acquisition of the current state distribution and the time-space evolution information of the cyanobacterial bloom in the lake coastal zone by using limited lake surrounding video monitoring equipment.
Description
Technical Field
The invention belongs to the field of lake water environment monitoring, and particularly relates to a real-time monitoring and space-time analysis method for blue algae bloom on a lake shore based on video monitoring equipment.
Background
In recent years, with the development of video monitoring technology, for most lakes (such as Taihu lake, honeycomb lake, Dian lake, and the like) in China, a certain amount of video monitoring equipment is usually laid along the shore for monitoring fish administration law enforcement, people flow in landscape areas, remote security and protection of equipment, and the like, which also provides a new idea for accurately extracting cyanobacterial blooms in the lakeshore zones of lakes. However, the traditional blue algae bloom monitoring method based on the video monitoring equipment has a plurality of defects: (1) the cyanobacterial bloom monitoring program does not take the difference of hardware environments of different servers into consideration, and the cyanobacterial bloom monitoring task is completed based on a single-thread serial computing mode, so that the monitoring efficiency is low; (2) the lake shore area has long and wide range, and the existing research can only obtain the cyanobacterial bloom strength information of discrete points based on a limited number of monitoring equipment, so that the real-time/near-real-time obtaining of the cyanobacterial bloom status information of the whole shore area is difficult to realize; (3) the existing research only focuses on the current situation information of the cyanobacterial bloom in the monitoring range, ignores the analysis of the time-space evolution situation, cannot realize the time-space change information of the cyanobacterial bloom strength of the whole coastal zone area, and cannot meet the decision requirement of the emergency prevention and control of the cyanobacterial bloom in the lake.
Disclosure of Invention
The invention aims to provide a real-time monitoring and time-space analysis method of the lake coastal zone cyanobacterial bloom based on video monitoring equipment, which realizes real-time mastering, standard exceeding alarm and time-space change analysis of the current situation information of the cyanobacterial bloom in the whole coastal zone area under the unattended condition and provides support for scientific prevention and control and emergency decision of the lake cyanobacterial bloom.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the full-automatic monitoring method of the cyanobacterial bloom on the lake shore based on the video monitoring equipment comprises the following steps:
step 1: setting the image capturing time and time interval of each video monitoring device, and capturing video key frames of the monitoring devices at regular time;
step 2: starting a data processing task based on a message transfer mechanism, carrying out batch processing on the captured video key frames, calculating the blue algae coverage of each video key frame in batch by using a self-adaptive multithreading method, and determining blue algae bloom space distribution, blue algae coverage and bloom strength data based on the blue algae coverage;
the number of threads for calculating the coverage of the blue algae is dynamically determined according to the program running hardware environment;
and step 3: based on the cyanobacterial bloom monitoring results of different point positions obtained by the annular lake video monitoring equipment, cyanobacterial bloom information of the whole annular lake shore zone area is obtained through online GIS spatial interpolation, a bloom intensity threshold value is set, and an alarm is automatically given when the cyanobacterial bloom intensity exceeds the threshold value; and based on the comparison of the intensity information of the cyanobacterial bloom in the coastal zone at different moments, the analysis of the space-time evolution situation of the cyanobacterial bloom intensity is realized.
As a further improvement of the present invention, in step 1, on-site debugging is performed on each video monitoring device in advance to obtain optimal spatial attitude parameters suitable for extracting the cyanobacterial bloom, including a horizontal rotation angle P, a vertical rotation angle T and a zoom multiple Z;
when capturing the video key frames, after adjusting each video monitoring device to the recorded optimal spatial attitude parameter, capturing the video key frame pictures according to the set image capturing time and time interval.
As a further improvement of the present invention, in step 1, when capturing a video key frame of a monitoring device, n sub-threads are established, where n is the number of the monitoring devices; adaptively determining a maximum number of threads N according to a hardware environment;
if N is less than or equal to N, simultaneously starting N sub-threads and controlling each front-end monitoring device to capture the key frame image;
if N is larger than N, finishing the key frame image capturing work in batches, firstly performing key frame image capturing of 1-N equipment according to the serial number of the video equipment of the monitoring equipment, and then performing key frame image capturing of N + 1-2N equipment until the key frame image capturing of all the front-end monitoring equipment is finished;
all the sub-threads simultaneously control corresponding video monitoring equipment to capture images according to preset image capturing moments and time intervals;
if N is larger than N, the time interval of batch image capturing is determined according to the set image capturing time and time interval.
And simultaneously controlling the corresponding video monitoring equipment to capture images by all the sub-threads according to the preset image capturing moment and time interval.
As a further improvement of the present invention, in step 1, the key frame images captured by the video monitoring devices are transmitted back to the server through the wireless network, and the images of the video monitoring devices are classified and stored based on the device numbers and the capturing time.
Furthermore, in order to ensure the timeliness of the extraction result of the cyanobacterial bloom, the time interval for capturing the key frame pictures by all the equipment monitoring equipment is less than or equal to 5 min.
As a further improvement of the present invention, in the step 2, the number of threads for calculating the coverage of the blue-green algae is determined by:
a. acquiring the running hardware environment of a computer program, including the size of a memory, the CPU main frequency and the Rui frequency;
b. setting the number of initial threads to be 1, and starting the threads;
c. starting a new thread and acquiring the CPU occupancy rate after the new thread is started;
d. judging whether the CPU occupancy rate exceeds a preset value: if the number of the threads exceeds the preset value, the number of the optimal threads is equal to the number of the threads started currently-1; otherwise, repeating c until the CPU occupancy rate exceeds the preset value. In order to solve the contradiction between the limited computer/server hardware configuration and the unlimited data processing efficiency requirement, the maximum thread number is determined in a self-adaptive manner according to different hardware environments, hardware resources are fully utilized, and the data processing efficiency is improved to the maximum extent. The preset value is preferably 90%, and 10% of safety space is reserved, so that the exception caused by insufficient hardware resources due to the starting of other temporary tasks in the server is avoided.
As a further improvement of the present invention, in the step 2, the batch processing includes:
i) performing orthorectification, denoising and light homogenizing treatment on the key frame picture; a certain included angle exists between the video monitoring equipment and the lake water surface, so that the captured image can generate geometric distortion, and the distortion is eliminated through geometric correction so as to accurately calculate the distribution range of the cyanobacterial bloom; the captured key frame image is inevitably influenced by the noise of the environment and the sensor, and the key frame image needs to be subjected to denoising processing, so that the interference of noise is reduced, and misjudgment and missed judgment are avoided; the captured key frame images have the characteristics of constant spatial range and time-varying illumination conditions, the complicated and variable illumination conditions cause the change of the characterization information of water quality/water color in the image data, the inconsistency among the key frame images caused by the change of the illumination conditions needs to be weakened, and the identification precision of the cyanobacterial bloom is improved from the perspective of time sequence;
ii) establishing a scene recognition model based on the deep convolutional neural network, and calculating the coverage rate of blue-green algae in the image; the deep learning technology is utilized to overcome the influence of complex background and variable environment on the extraction precision of the cyanobacterial bloom;
and iii) dividing the water bloom strength grade according to the calculation result of the blue algae coverage rate.
As a further improvement of the present invention, in ii), the image is divided into a plurality of blocks, and the category of each image block is predicted based on a scene recognition model; counting the number of the image blocks divided into the blue algae, and estimating the coverage rate of the blue algae in the original image.
As a further improvement of the invention, in the step 2, the calculated cyanobacterial bloom space distribution, cyanobacterial coverage and bloom strength data are classified and stored according to the equipment number and the capturing time.
As a further improvement of the invention, in the step 3, a topological relation between longitude and latitude coordinates of the circulating lake video monitoring equipment and a coastal zone is established, and the cyanobacterial bloom strength distribution of the whole coastal zone is obtained.
As a further improvement of the invention, the step 3 further includes obtaining the time-space evolution information of the cyanobacterial bloom on the lake shore based on the long-time-sequence cyanobacterial bloom spatial distribution data obtained by each video monitoring device.
The analysis method of the invention realizes that all data processing tasks are automatically executed by computer programs, and the current situation distribution and change trend information of the cyanobacterial bloom in the lakeshore zone can be automatically obtained without manual intervention.
The real-time monitoring and time-space analysis method for the lake coastal zone cyanobacterial bloom based on the video monitoring equipment is designed based on the video monitoring means aiming at the problems that the traditional lake cyanobacterial bloom monitoring means has incomplete, inaccurate and untimely monitoring of key areas and the like, so that the real-time grasping of the cyanobacterial bloom information of the whole coastal zone area, automatic alarm of standard exceeding information and time-space evolution analysis are realized; meanwhile, based on technical methods such as data communication, multithreading, GIS space analysis and the like, the efficiency of data capture and processing is greatly improved, the fact that a program can fully utilize resources in different hardware environments is ensured, the calculation efficiency is improved, unattended operation in the whole process of data capture, data processing, data analysis, data storage and data display is achieved, and decision support is provided for scientific prevention and control and emergency treatment of cyanobacterial bloom.
It should be understood that all combinations of the foregoing concepts and additional concepts described in greater detail below can be considered as part of the inventive subject matter of this disclosure unless such concepts are mutually inconsistent. In addition, all combinations of claimed subject matter are considered a part of the presently disclosed subject matter.
The foregoing and other aspects, embodiments and features of the present teachings can be more fully understood from the following description taken in conjunction with the accompanying drawings. Additional aspects of the present invention, such as features and/or advantages of exemplary embodiments, will be apparent from the description which follows, or may be learned by practice of specific embodiments in accordance with the teachings of the present invention.
Drawings
The drawings are not necessarily to scale. In the drawings, each identical or nearly identical component that is illustrated in various figures may be represented by a like numeral. For purposes of clarity, not every component may be labeled in every drawing. Embodiments of various aspects of the present invention will now be described, by way of example, with reference to the accompanying drawings, in which:
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a key frame data grabbing and processing method based on the multithreading technology.
Fig. 3 is a result of timed and automatic capturing of key frame images of all base video monitoring equipment on the lakeside.
FIG. 4 shows the result of inquiring and displaying the information of the cyanobacterial bloom in the bank.
FIG. 5 shows the result of the query of the cyanobacterial bloom coverage rate change information.
FIG. 6 shows the result of the topological relation construction between the ring lake video monitoring equipment and the coastal zone.
FIG. 7 is the result of on-line map of the current situation of cyanobacterial bloom in the bank.
FIG. 8 is the interface for inquiring the information of the cyanobacterial bloom in the bank.
FIG. 9 shows the time-space evolution analysis result of cyanobacterial bloom in the lakeshore.
Detailed Description
In order to better understand the technical content of the present invention, specific embodiments are described below with reference to the accompanying drawings.
In this disclosure, aspects of the present invention are described with reference to the accompanying drawings, in which a number of illustrative embodiments are shown. Embodiments of the present disclosure are not necessarily defined to include all aspects of the invention. It should be appreciated that the various concepts and embodiments described above, as well as those described in greater detail below, may be implemented in any of numerous ways, as the disclosed concepts and embodiments are not limited to any one implementation. In addition, some aspects of the present disclosure may be used alone, or in any suitable combination with other aspects of the present disclosure.
Example 1
This example illustrates a specific implementation of the present invention.
The embodiment utilizes the lake surrounding video monitoring equipment to carry out real-time and automatic monitoring on the cyanobacterial bloom on the lake shore, and the specific implementation process is as follows: firstly, presetting an optimal space attitude suitable for blue-green algae extraction for each video monitoring device, namely setting three parameters of P (horizontal angle), T (vertical angle) and Z (zoom multiple); then, acquiring real-time video stream data of each video monitoring device based on a data communication related method, setting a key frame capturing time interval of the video monitoring device according to specific service requirements, and periodically driving each device to capture key frame images; transmitting the key frame images captured by all the equipment back to a server through a wireless network for storage, starting a cyanobacterial bloom extraction program after the task is completed, and acquiring cyanobacterial bloom strength information; an online GIS space analysis method is designed, based on the cyanobacterial bloom strength information acquired by each video monitoring point location, the information such as the cyanobacterial bloom space distribution, the time-space evolution and the like of the whole coastal zone area is dynamically mastered in real time, and the automatic alarm of the over-standard point location is realized.
The implementation of the foregoing method is specifically described below, as an exemplary description, with reference to the figures.
And (3) carrying out field debugging on each video monitoring device in advance before executing a processing task, and acquiring the optimal space attitude parameters suitable for extracting the cyanobacterial bloom, namely P (horizontal angle), T (vertical angle) and Z (zoom multiple).
The flow of the method is shown in fig. 1, and the method comprises the following steps:
step 1: capturing a key frame image;
the method comprises the following steps of grabbing key frame images of the front-end monitoring equipment in batches according to preset image grabbing moments and time intervals by using an adaptive multithreading technology, and improving image grabbing efficiency:
establishing N sub-threads (N is the number of monitoring equipment), and adaptively determining the maximum thread number N according to the hardware environment; if N is less than or equal to N, simultaneously starting N sub-threads and controlling each front-end monitoring device to capture the key frame image; if N is larger than N, finishing the key frame image capturing work in batches, firstly performing key frame image capturing of 1-N equipment according to the ID number (video monitoring equipment number), and then performing key frame image capturing of N + 1-2N equipment until the key frame image capturing of all front-end monitoring equipment is finished; as shown in fig. 2;
the key frame image data captured by the front-end video monitoring device is transmitted back to the server through the wireless network, and the data is organized according to the device number _ year-month-day-time, as shown in fig. 3.
And step 3: according to the designed blue algae coverage extraction method, the maximum thread number of the blue algae water bloom coverage calculation program is determined in a self-adaptive manner by combining with a hardware environment (automatic acquisition) operated by the program, and then the blue algae water bloom coverage is calculated in batch by utilizing a multithreading mechanism on the acquired key frame image data.
Adaptively determining the maximum number of threads according to the program operating environment as follows:
a. acquiring the running hardware environment of the automatic blue algae bloom extracting and analyzing program through a computer program, wherein the running hardware environment comprises the memory size, the CPU main frequency and the Rui frequency;
b. setting the number of initial threads to be 1, and starting the threads;
c. starting a new thread and acquiring the CPU occupancy rate after the thread is started;
d. judging whether the CPU occupancy rate exceeds the standard (more than 90%, reserving 10% of safety space, avoiding the abnormal condition caused by insufficient hardware resources due to the starting of other temporary tasks in the server): if the number exceeds the standard, the optimal thread number is equal to the number of the threads started currently, namely-1; if not, repeating c until the CPU occupancy rate exceeds the standard;
and performing batch calculation of the cyanobacterial bloom coverage on the acquired key frame image data by utilizing a multithreading mechanism, wherein the method comprises the following steps:
a. and preprocessing the captured key frame picture.
In this embodiment, the captured key frame picture is sequentially subjected to ortho-rectification, denoising processing and dodging processing. The orthorectification adopts a collinear equation model to correct the inclination/photographic difference; denoising the image by filtering; and the light homogenizing treatment is carried out in a histogram adjustment mode, so that the difference of illumination conditions is weakened.
b. Carrying out blue algae coverage rate calculation on the preprocessed image;
establishing a scene recognition model by using a deep convolutional neural network: dividing an original image into a plurality of small image blocks (such as 100 x 100 pixels), predicting the category (blue algae or water body) of each image block by using a scene recognition model, further counting the number of the image blocks divided into the blue algae, and estimating the coverage rate of the blue algae in the original image.
c. And (4) dividing the water bloom grade according to the result of the coverage rate of the blue algae.
The water bloom strength grading method comprises the following steps: (r is the area ratio of water bloom)
r is more than 50 percent, and the bloom strength is first grade;
r is more than 30 percent and less than or equal to 50 percent, and the bloom strength is of the second grade;
r is more than or equal to 0 and less than or equal to 30 percent, and the bloom strength is three-grade.
And 4, step 4: organizing the key frame images and the processing result data captured by the front-end video monitoring equipment according to the format of 'equipment number _ year-month-day-time', and supporting the query and display of results according to the number of the monitoring equipment and the monitoring time, as shown in fig. 4; meanwhile, the cyanobacterial bloom change information at the same point can be inquired and contrasted and analyzed based on the long-time sequence monitoring data, as shown in fig. 5 and 8.
And 5: judging according to the cyanobacterial bloom strength information acquired by each video monitoring device by combining with a bloom strength threshold value, and automatically alarming aiming at the overproof point; establishing a topological relation between the coordinates (longitude and latitude) of the lake encircling video monitoring equipment and the coastal zone area, as shown in FIG. 6; designing a GIS (geographic information system) online space analysis method, generating a blue algae water bloom strength distribution thematic map of the whole coastal zone in real time, and realizing real-time grasping of the current blue algae water bloom information of the whole lakeside coastal zone, as shown in FIG. 7; and acquiring the time-space evolution information of the cyanobacterial bloom on the lake shore based on the long-time-sequence cyanobacterial bloom spatial distribution data acquired by each video monitoring device, as shown in fig. 8 and 9.
Example 2
This example illustrates the comparison of the efficiency of extraction of cyanobacterial bloom with the existing methods.
Taking three lakes of a nested lake, a Dian lake and a Tianmu lake as examples, under the same server and network configuration conditions, comparing and analyzing the time consumption of the blue algae water bloom extraction process of the surrounding lake video monitoring equipment by using the method (parallel calculation based on the adaptive multithreading technology) and the existing blue algae water bloom extraction method (traditional single-thread serial calculation) based on the video monitoring equipment respectively, and the results are shown in the following table 1. Obviously, under the same conditions, the method has obvious advantages in the aspect of the efficiency of extracting the cyanobacteria bloom.
TABLE 1 comparison test results of cyanobacterial bloom extraction efficiency
Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention.
Claims (10)
1. A method for monitoring and analyzing cyanobacterial bloom on a lake shore based on video monitoring equipment is characterized by comprising the following steps:
step 1: setting the image capturing time and time interval of each video monitoring device, and capturing video key frames of the monitoring devices at regular time;
step 2: starting a data processing task based on a message transfer mechanism, carrying out batch processing on the captured video key frames, calculating the blue algae coverage of each video key frame in a multi-thread manner, and determining blue algae bloom space distribution, blue algae coverage and bloom strength data based on the blue algae coverage;
the number of threads for calculating the coverage of the blue algae is dynamically determined according to the program running hardware environment;
and step 3: based on the cyanobacterial bloom monitoring results of different point locations acquired by the lake surrounding video monitoring equipment, cyanobacterial bloom information of the whole lake surrounding shore zone area is acquired through online GIS spatial interpolation, a bloom intensity threshold value is set, and an alarm is automatically given when the cyanobacterial bloom intensity exceeds the threshold value; and based on the comparison of the intensity information of the cyanobacterial bloom in the coastal zone at different moments, the analysis of the space-time evolution situation of the cyanobacterial bloom intensity is realized.
2. The method according to claim 1, wherein in the step 1, each video monitoring device is debugged in advance on site to obtain optimal spatial attitude parameters suitable for the extraction of the cyanobacterial bloom, wherein the optimal spatial attitude parameters comprise a horizontal rotation angle P, a vertical rotation angle T and a zoom multiple Z;
when capturing the video key frames, after adjusting each video monitoring device to the recorded optimal spatial attitude parameter, capturing the video key frame pictures according to the set image capturing time and time interval.
3. The method according to claim 1, wherein in step 1, the monitoring device establishes the capturing of the video key framenThe sub-threads are,n= number of monitoring devices; adaptively determining a maximum number of threads according to a hardware environmentN；
If it isn≤NThen start at the same timenThe sub-threads control all front-end monitoring equipment to capture key frame images in parallel;
if it isn＞NFinishing the work of capturing the key frame images in batches, and performing 1 to 1 according to the serial numbers of the video equipment of the monitoring equipmentNCapturing key frame images of the equipment, and performing the second step after the key frame images are capturedN+1~2NIs provided withCapturing the prepared key frame images until all the key frame images of the front-end monitoring equipment are captured;
all the sub-threads simultaneously control corresponding video monitoring equipment to capture images according to preset image capturing moments and time intervals;
if it isn＞NAnd the time interval of batch grapping is determined according to the set grapping time and the time interval.
4. The method according to claim 1, wherein in step 1, the key frame images captured by the video monitoring devices are transmitted back to the server through a wireless network, and the images of the video monitoring devices are classified and stored based on the device numbers and the capturing time.
5. The method of claim 1, wherein in the step 2, the number of threads for calculating the coverage of the blue-green algae is determined by the following method:
a. acquiring the running hardware environment of a computer program, including the size of a memory, the CPU main frequency and the Rui frequency;
b. setting the number of initial threads to be 1, and starting the threads;
c. starting a new thread and acquiring the CPU occupancy rate after the new thread is started;
d. judging whether the CPU occupancy rate exceeds a preset value: if the number of the threads exceeds the preset value, the optimal number of the threads = the number of the threads started at present-1; otherwise, repeating c until the CPU occupancy rate exceeds the preset value.
6. The method of claim 1, wherein in step 2, the batch processing comprises:
i) performing orthorectification, denoising and light homogenizing treatment on the key frame picture;
ii) establishing a scene recognition model based on the deep convolutional neural network, and calculating the coverage rate of blue-green algae in the image;
and iii) dividing the water bloom strength grade according to the calculation result of the blue algae coverage rate.
7. The method as claimed in claim 6, wherein in ii), the image is divided into a plurality of blocks, and the category of each image block is predicted based on a scene recognition model; counting the number of the image blocks divided into the blue algae, and estimating the coverage rate of the blue algae in the original image.
8. The method as claimed in claim 4, wherein in the step 2, the calculated cyanobacterial bloom space distribution, cyanobacterial coverage and bloom strength data are classified and stored according to the equipment number and the capture time.
9. The method as claimed in claim 4, wherein in the step 3, the topological relation between longitude and latitude coordinates of the lake encircling video monitoring equipment and the coastal zone is established, and the cyanobacterial bloom intensity distribution of the whole coastal zone is obtained.
10. The method as claimed in claim 4, wherein the step 3 further comprises obtaining the space-time evolution information of the cyanobacterial bloom on the lake shore based on the long-time cyanobacterial bloom space distribution data obtained by each video monitoring device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110834926.0A CN113627280A (en) | 2021-07-23 | 2021-07-23 | Method for monitoring and analyzing cyanobacterial bloom in lake shore zone based on video monitoring equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110834926.0A CN113627280A (en) | 2021-07-23 | 2021-07-23 | Method for monitoring and analyzing cyanobacterial bloom in lake shore zone based on video monitoring equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113627280A true CN113627280A (en) | 2021-11-09 |
Family
ID=78380696
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110834926.0A Pending CN113627280A (en) | 2021-07-23 | 2021-07-23 | Method for monitoring and analyzing cyanobacterial bloom in lake shore zone based on video monitoring equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627280A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108675454A (en) * | 2018-04-28 | 2018-10-19 | 中国科学院南京地理与湖泊研究所 | A kind of large-scale shallow water lake blue algae wawter bloom development Whole Process Control method |
| CN108982794A (en) * | 2018-07-13 | 2018-12-11 | 中国科学院南京地理与湖泊研究所 | A kind of Cyanophyta algal bloom monitoring method and system based on digital high-definition image |
| CN109144699A (en) * | 2018-08-31 | 2019-01-04 | 阿里巴巴集团控股有限公司 | Distributed task dispatching method, apparatus and system |
| CN111104976A (en) * | 2019-12-12 | 2020-05-05 | 南京大学 | Time sequence image-based blue-green algae coverage rate calculation method |
| CN111464331A (en) * | 2020-03-03 | 2020-07-28 | 深圳市计通智能技术有限公司 | Control method and system for thread creation and terminal equipment |
| CN112232234A (en) * | 2020-10-20 | 2021-01-15 | 生态环境部卫星环境应用中心 | Remote sensing-based method and device for evaluating cyanobacterial bloom strength in inland lakes and reservoirs |
| CN112766202A (en) * | 2021-01-27 | 2021-05-07 | 河海大学 | Blue algae information real-time indication method based on satellite remote sensing, storage medium and equipment |
-
2021
- 2021-07-23 CN CN202110834926.0A patent/CN113627280A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108675454A (en) * | 2018-04-28 | 2018-10-19 | 中国科学院南京地理与湖泊研究所 | A kind of large-scale shallow water lake blue algae wawter bloom development Whole Process Control method |
| CN108982794A (en) * | 2018-07-13 | 2018-12-11 | 中国科学院南京地理与湖泊研究所 | A kind of Cyanophyta algal bloom monitoring method and system based on digital high-definition image |
| CN109144699A (en) * | 2018-08-31 | 2019-01-04 | 阿里巴巴集团控股有限公司 | Distributed task dispatching method, apparatus and system |
| CN111104976A (en) * | 2019-12-12 | 2020-05-05 | 南京大学 | Time sequence image-based blue-green algae coverage rate calculation method |
| CN111464331A (en) * | 2020-03-03 | 2020-07-28 | 深圳市计通智能技术有限公司 | Control method and system for thread creation and terminal equipment |
| CN112232234A (en) * | 2020-10-20 | 2021-01-15 | 生态环境部卫星环境应用中心 | Remote sensing-based method and device for evaluating cyanobacterial bloom strength in inland lakes and reservoirs |
| CN112766202A (en) * | 2021-01-27 | 2021-05-07 | 河海大学 | Blue algae information real-time indication method based on satellite remote sensing, storage medium and equipment |
Non-Patent Citations (2)
| Title |
|---|
| 段洪涛;万能胜;邱银国;刘刚;陈青;罗菊花;陈远;齐天赐;: "富营养化湖库天空地一体化监控平台系统设计与实践", 湖泊科学, vol. 32, no. 05, pages 1399 - 1401 * |
| 谢涛;纪道斌;尹卫平;朱冠霖;刘德富;孔松;: "三峡水库不同下泄流量香溪河水动力特性与水华的响应", 中国农村水利水电, no. 11 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111967393A (en) | Helmet wearing detection method based on improved YOLOv4 | |
| CN113887412B (en) | Detection method, detection terminal, monitoring system and storage medium for pollution emission | |
| CN101599175B (en) | Detection method for determining alteration of shooting background and image processing device | |
| WO2021120591A1 (en) | Systems and methods for adjusting a monitoring device | |
| CN109413411A (en) | A kind of blank screen recognition methods, device and the server of monitoring circuit | |
| CN111242096B (en) | People number gradient-based people group distinguishing method | |
| CN113160023A (en) | Land utilization checking system | |
| CN100469138C (en) | Power transformer draught fan state recognizing method based on video monitoring and image recognition | |
| CN102724541B (en) | Intelligent diagnosis and recovery method for monitoring images | |
| CN114187543A (en) | Safety belt detection method and system in high-altitude power operation scene | |
| CN102063659B (en) | Method, server and system for collecting and making electronic photo | |
| CN117768610A (en) | High-speed railway perimeter intrusion risk monitoring method and system based on multi-target recognition | |
| CN112422818A (en) | Intelligent screen dropping remote detection method based on multivariate image fusion | |
| CN113627280A (en) | Method for monitoring and analyzing cyanobacterial bloom in lake shore zone based on video monitoring equipment | |
| CN112633157A (en) | AGV working area safety real-time detection method and system | |
| KR102040562B1 (en) | Method to estimate visibility distance using image information | |
| CN117292111A (en) | Offshore target detection and positioning system and method combining Beidou communication | |
| CN109145820B (en) | River channel position marking method based on video dynamic images | |
| CN112883755A (en) | Smoking and calling detection method based on deep learning and behavior prior | |
| CN114972740A (en) | Automatic ship sample collection method and system | |
| JP4675501B2 (en) | Meter monitoring system and meter monitoring method | |
| CN110136104A (en) | Image processing method, system and medium based on unmanned aerial vehicle station | |
| CN112396024A (en) | Forest fire alarm method based on convolutional neural network | |
| WO2023240651A1 (en) | Image processing method and apparatus | |
| CN112668442B (en) | Data acquisition and networking method based on intelligent image processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |